Microsoft AI Video App Makes Mona Lisa Painting Sing; Video Gets Over 7 Million Views

A video of the iconic painting Monalisa singing and rapping has gone viral, with over seven million views till now and still increasing. This video was initially shared on Microsoft’s page as they published the paper regarding a new AI app called VASA 1, a framework for generating lifelike talking faces of virtual characters with appealing visual affective skills (VAS), given a single static image and a speech audio clip.

VASA-1 is capable of not only producing lip movements that are exquisitely synchronized with the audio but also capturing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness.

Also Read: Microsoft’s $2.9B Boost for Japan’s AI and Cloud Capabilities

Here is a post on X that captures Mona Lisa’s rapping video.

What do X users have to say about this AI video?

A few users joked about the video and shared their comments.

• One of the users shared “The Mona Lisa clip had me rolling on the floor laughing,”.
• Another said, “Mona Lisa rapping Paparazzi is wild,”
• A third wondered, “ ”Oh, man. If only Da Vinci could witness this.”
• The fourth one joked, “ “The Mona Lisa one is unbelievable, haha,”

While a few users were worried about the increasing number of fakes and misuse of this technology,

• The fifth user commented, “Cool demo! But very soon, people will have difficulty telling a real person from a fake one just by watching video content. This will bring a huge amount of fraud and scams on the Internet. It is now imperative to pioneer novel methods to restore and fortify trust in the age of AI,”.
• Followed by the sixth user comment, “Creepy? Fascinating? For one thing, deepfake potential just grew exponentially, but opens up some interesting creative possibilities as well.”

Also Read: Mustafa Suleyman announces new Microsoft AI hub in London

According to the official Microsoft blog, there is no timeline declared and the technology is still in the testing phase. The company further wrote, “ Our research focuses on generating visual affective skills for virtual AI avatars, aiming for positive applications. It is not intended to create content that is used to mislead or deceive. While acknowledging the possibility of misuse, it’s imperative to recognize the substantial positive potential of our technique. “ 

Microsoft further warned that “we have no plans to release an online demo, API, product, additional implementation details, or any related offerings until we are certain that the technology will be used responsibly and following proper regulations. “